According to IARC Monographs on the Evaluation of Carcinogenic Risks to Humans:
Tobacco smoke and involuntary smoking (Vol. 83. 2004, Lyon: IARC Press), people with the highest lung cancer risks are those who:
- Smoke the most cigarettes per day
- Smoke over long periods of time, and
- Start smoking young
We cannot yet exactly calculate a person's lung cancer risk based on how many cigarettes they smoke or the number years they have been a smoker. Yet studies have shown that lung cancer risk is greatest among those who smoke the most cigarettes over the longest period of time. As such, altering this hypothesis slightly, you and your team collect the following data to demonstrate whether or not there is an existing evidence-based relationship between the length of smoking time and visits to a clinician based on thoracic symptom-related issues.
After reviewing five years worth of randomized charts of self-proclaimed smokers in a hospital system based in Philadelphia, you identify the following data:
|
Length of years smoking
|
# Of visits to a clinician due to thoracic issues
|
Length of years smoking
|
# Of visits to a clinician due to thoracic issues
|
Length of years smoking
|
# Of visits to a clinician due to thoracic issues
|
|
14
|
6
|
44
|
7
|
35
|
12
|
|
21
|
7
|
41
|
11
|
4
|
2
|
|
21
|
2
|
40
|
5
|
5
|
1
|
|
21
|
3
|
27
|
8
|
10
|
2
|
|
19
|
2
|
29
|
1
|
10
|
3
|
|
15
|
1
|
30
|
9
|
13
|
3
|
*Please note that this is a random list of data that does not include all of the patient charts
that were reviewed for this study.
1) Create a scatter plot diagram of the data provided.
2) Provide evidence on whether there is a strong, weak, or non-existent correlation between the two variables?
3) Provide evidence on whether there is a strong or weak regression (predicted pattern of success over time)?
4) What is your analysis of these results?